Re:Can LLMs invent better ways to train LLMs?
by luke-stanley on Thursday June 13, 2024 @07:14AM
(#40668151)
The project sounds quite interesting but I'm not sure running it is going to work!
The code `gpt_model = "gpt4_20231230_1106preview"` is not using a valid model name as best as I can tell, so it seems unlikely to work - from https://github.com/SakanaAI/DiscoPOP/blob/main/scripts/launc...
Unusually, the issue section doesn't exist so I can't provide feedback to them that way. But luchris429's repo does have it so will do so there.
Maybe it's dead code. Still, it's wrong.
[ Parent
| on HN ]
Re:Can LLMs invent better ways to train LLMs?
by luchris429 on Thursday June 13, 2024 @11:41AM
(#40671032)
Author here! Thanks for pointing that out. The correct model name is indeed "gpt-4" instead of "gpt_model = 'gpt4_20231230_1106preview'". We were previously using an Azure endpoint, which is why the model name is different.
While I understand the frustration, I assure you that the rest of the code is functional. This was a simple oversight and should be a trivial fix. I appreciate your feedback and understanding.